Empowering Vision Language Models for Training-Free Visual Search via Context-Aware Scanpath Simulation.

@inproceedings{wang-2026-empowering, author = {Haoran Wang and Dan Wan}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{Empowering Vision Language Models for Training-Free Visual Search via Context-Aware Scanpath Simulation}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {206--214}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810610}, doi = {https://doi.org/10.1145/3805622.3810610} }